AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

SOLAR: Second-Order Loss and Attention for Image Retrieval

Tony Ng, Vassileios Balntas, Yurun Tian, Krystian Mikolajczyk

ECCV 2020 · Label-efficient and robust learning › Recognition and long-tail · approach: Correspondence and causal representation learning · 117 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add second-order similarity (SOS) loss to GeM baseline (ablation)ResNet101-GeM · ROxf HardmAP: 44.3 -> 44.9Improved
add SOA block after conv4_x (ablation)ResNet101-GeM · ROxf HardmAP: 44.3 -> 45.7Improved
add SOA block after conv5_x (ablation)ResNet101-GeM · ROxf HardmAP: 44.3 -> 45.9Improved
add consecutive SOA blocks after conv4_x and conv5_x (ablation)ResNet101-GeM · ROxf HardmAP: 44.3 -> 46.9Improved
add SOS loss on top of SOA blocks (full SOLAR) (ablation)ResNet101+SOA · ROxf HardmAP: 46.9 -> 47.9Improved
add SOS loss on top of SOA blocks (full SOLAR) (ablation)ResNet101+SOA · RPar HardmAP: 63.7 -> 64.5Improved
add SOLAR instead of GeM baseline on 1M distractorsResNet101-GeM · RPar+R1M HardmAP: 29.8 -> 33.4Improved
add SOLAR instead of GeM baselineResNet101-GeM · ROxf MediummAP: 67.3 -> 69.9Improved
add SOA block after layer 3 of SOSNet (ablation)SOSNet+ · UBC PatchesFPR@95 mean: 1.138 -> 1.065Improved
add SOA block after low-resolution layer 6 of SOSNet (ablation)SOSNet+ · UBC PatchesFPR@95 mean: 1.138 -> 1.380Hurt
insert SOA at consecutive layers (3,4) rather than non-consecutive (3,5) (ablation)SOSNet+ · HPatches Patch RetrievalmAP: 0.17%Improved
insert SOA at consecutive layers (4,5) rather than (4,6) (ablation)SOSNet+ · HPatches Patch RetrievalmAP: 0.45%Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy